From 2cd7542f975106f7fc072f88f9beca104ba11ca3 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Sat, 23 May 2026 11:16:13 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: xiaomi-open-source/Xiaomi-MiMo-VL-Miloco-7B Source: Original Platform --- .gitattributes | 55 ++ LICENSE | 18 + README.md | 94 ++++ added_tokens.json | 24 + chat_template.json | 3 + config.json | 68 +++ generation_config.json | 7 + merges.txt | 3 + model-00001-of-00004.safetensors | 3 + model-00002-of-00004.safetensors | 3 + model-00003-of-00004.safetensors | 3 + model-00004-of-00004.safetensors | 3 + model.safetensors.index.json | 832 +++++++++++++++++++++++++++++++ preprocessor_config.json | 29 ++ special_tokens_map.json | 31 ++ tokenizer.json | 3 + tokenizer_config.json | 209 ++++++++ vocab.json | 3 + 18 files changed, 1391 insertions(+) create mode 100644 .gitattributes create mode 100644 LICENSE create mode 100644 README.md create mode 100644 added_tokens.json create mode 100644 chat_template.json create mode 100644 config.json create mode 100644 generation_config.json create mode 100644 merges.txt create mode 100644 model-00001-of-00004.safetensors create mode 100644 model-00002-of-00004.safetensors create mode 100644 model-00003-of-00004.safetensors create mode 100644 model-00004-of-00004.safetensors create mode 100644 model.safetensors.index.json create mode 100644 preprocessor_config.json create mode 100644 special_tokens_map.json create mode 100644 tokenizer.json create mode 100644 tokenizer_config.json create mode 100644 vocab.json diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e149b80 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,55 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text + +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +merges.txt filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text +vocab.json filter=lfs diff=lfs merge=lfs -text +model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text +model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/LICENSE b/LICENSE new file mode 100644 index 0000000..d252990 --- /dev/null +++ b/LICENSE @@ -0,0 +1,18 @@ +Xiaomi Miloco License Agreement +Copyright (C) 2025 Xiaomi Corporation. +The ownership and intellectual property rights in the entire content of Xiaomi Miloco project provided under this license, including but not limited to web_ui code, server code, ai_engine code, Xiaomi Home Cloud Service API interfaces, Xiaomi Home SDK, Xiaomi Home Device Model Context Protocol (MCP) services, Xiaomi MiMo-VL-Miloco model code and weight files (collectively, "Licensed Work") , whether provided in source code, object code, or any other form, are exclusively owned by Xiaomi. Subject to the terms and conditions of this License, Xiaomi hereby grants you a personal, limited, non-exclusive, non-transferable, non-sublicensable and roylaty-free license to reproduce, use, modify and distribute the Licensed Work only for your use of Xiaomi Miloco project for non-commercial purposes. For the avoidance of doubt, Xiaomi does not authorize you to use the Licensed Work for any other purpose, including but not limited to use Licensed Work to develop applications (APP), Web services, and other forms of software. +You may reproduce and distribute copies of the Licensed Work, with or without modifications, whether in source or object form, provided that you must give any other recipients of the Licensed Work a copy of this License and retain all copyright and disclaimers. +Xiaomi provides the Licensed Work on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied, including, without limitation, any warranties, undertakes or conditions of TITLE, NO ERROR OR OMISSION, CONTINUITY, RELIABILITY, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A PARTICULAR PURPOSE. In any event, you are solely responsible for any direct, indirect, special, incidental or consequential damages or losses arising from the use or redistribute of the Licensed Work or the inability to use the Licensed Work. +Xiaomi reserves all rights not expressly granted to you in this License. Except for the rights expressly granted by Xiaomi under this License, Xiaomi does not authorize you in any form to use the trademarks, copyrights or other forms of intellectual property rights of Xiaomi and its affiliates, including, without limitation, without obtaining other written permission from Xiaomi, you shall not use "Xiaomi", "Mijia" and other words related to Xiaomi or words that may make the public associate with Xiaomi in any form to publicize or promote the software or hardware devices that using the Licensed Work. +Xiaomi has the right to immediately terminate your all authorization under this License in the event: +you assert patent invalidation, litigation or other claims against patents or other intellectual property rights of Xiaomi or its affiliates; or +you make, have made, manufacture, sell or offer to sell the products that knock off Xiaomi or its affiliates' products. + +版权声明 (C) 2025 小米 +在本许可证下提供的Xiaomi Miloco项目的全部内容，包括但不限于前端代码、主服务代码、大模型推理服务代码、米家云服务API接口、米家SDK、米家设备MCP服务、Xiaomi MiMo-VL-Miloco模型的代码及其权重文件（统称为“授权作品”），无论以源代码、目标代码或其他形式提供，授权作品的所有权及知识产权均归小米所有。小米在此授予您一项个人的、有限的、非排他的、不可转让的、不可转授权的、免费的权利，仅限于您为非商业性目的使用Xiaomi Miloco项目而复制、使用、修改、分发授权作品。为避免疑义，本许可证未授权您将授权作品用于任何其他用途，包括但不限于开发应用程序（APP）、Web 服务以及其他形式的软件等。 +您在重新分发授权作品时，无论修改与否，无论以源码形式或目标代码形式，您均需保留本授权作品中的版权标识、免责声明及本许可证的副本。 +授权作品是按“现状”分发的，小米不对授权作品承担任何明示或暗示的保证或担保，包括但不限于对授权作品没有错误或疏漏、持续性、可靠性、适用于某一特定用途或不侵权等的保证、声明或承诺。在任何情况下，对于因使用授权作品或无法使用授权作品而引起的任何直接、间接、特殊、偶然或后果性损害或损失，您需自行承担全部责任。 +本许可证中未明确授予的所有权利均予保留，除本许可证明确授予您的权利外，小米未以任何形式授权您使用小米及小米关联公司的商标、著作权或其他任何形式的知识产权，例如在未获得小米另行书面许可的情况下，您不得使用“小米”、“米家”等与小米相关的字样或其他会使得公众联想到小米的字样对您使用授权作品的软件或搭载授权作品的硬件做任何形式的宣传或推广。 +在下述情况下，小米有权立即终止对您依据本许可证获得的授权： +您对小米或其关联公司的专利或其他知识产权提起专利无效、诉讼或其他主张；或， +您生产、制造（含委托制造）、销售（含委托销售）模仿或复制小米产品（包含小米关联公司的产品）的山寨产品。 \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..10c2b48 --- /dev/null +++ b/README.md @@ -0,0 +1,94 @@ +
+ + + Xiaomi-MiMo-Vl-Miloco + +
+ + +
+ +
+ 🤗 HuggingFace +  | + 🤖️ ModelScope +
+
+ +
+ +## 介绍 + +欢迎体验Xiaomi MiMo-VL-Miloco开源项目——首个开源的、多模态的家庭场景理解大模型！ + +### 🤗 核心亮点 +- 基于MiMo-VL-7B：强大的视觉-语言基座，具备可靠的视频理解与指令遵循能力。 +- 为家庭场景而设计：能识别日常活动（电子竞技、健身锻炼、看电视、阅读等），并识读常见的手势，如比耶、点赞、张开手掌、OK，甚至比6手势。 +- 通用能力保持：训练策略结合了SFT和RL，MiMo-Vl-Miloco不仅拥有出色家庭场景理解能力，而且在通用任务上依然有较强的竞争力。 + +### 🌟 训练笔记 + +我们精心设计了两阶段优化策略，在保持模型基础的通用能力的同时，大幅提升模型的家庭场景理解能力。 + +#### 阶段 一: 监督微调 (SFT) + +我们首先关注如何提升模型在家庭场景中的理解能力。通过构建少量高质量的数据集，我们在模型高效学习与推理效率之间取得了良好的平衡。 + +- 构造思维链数据：我们通过构造思维链数据，让模型高效学习家庭场景知识。 +- 优化推理效率：通过采用“受限预算”的推理方式训练，能促使模型在推理阶段生成简洁明了的回答。 + +#### 阶段 二: 强化学习 (RL) + +在监督微调的基础上，我们引入基于GRPO的强化学习算法来提升模型的综合性能: + +- 高效的训练数据：我们采用了[Time-R1](https://arxiv.org/abs/2503.13377) (我们的工作已经被NeurIPS 2025接受）的数据策略来构建多domain的高效训练数据。 +- 通用能力保持：在进行家庭场景专项优化时，维持原有的理解与语言生成能力。 + +简而言之：Xiaomi MiMo-VL-Miloco 就像你的模范室友——既友善又目光敏锐，擅长识别家中的日常事务，同时依然能适应更广阔的世界。 + +### 😉 模型指南 + +模型权重及其量化版本均已开源： + +- #### [**MiMo-VL-Miloco-7B**](https://modelscope.cn/models/xiaomi-open-source/Xiaomi-MiMo-VL-Miloco-7B) + - 适合绝大多数用户深度体验。 + +- #### [**MiMo-VL-Miloco-7B-GGUF**](https://modelscope.cn/models/xiaomi-open-source/Xiaomi-MiMo-VL-Miloco-7B-GGUF) + - 混合精度量化版本。适合计算资源受限的场景。 + +## 性能表现 + +### 家庭场景理解能力评估 (F1-Score) +- MiMo-VL-Miloco-7B无论是在手势识别的场景，还是在常见的家庭场景理解上，都达到了领先水平。 +
+ + Accuracy & Recall + +
+ +### 通用能力评估 +在家庭场景理解下，我们重点关注的是视频、图像感知能力，以及模型的推理能力。 +- 在Video的三个benchmark上（Video-MME/Video-MMMU/Charades-STA）基座能力得到了明显的提升 +- 在通用能力的MMMU-Pro上，基座能力也都得到了显著的提升（10+%） +- 令人意外的是，随着视频、图像理解能力的提升，纯文本任务MMLU-Pro也取得了一定的提升。 +- 在文档理解、OCR、数学类等任务上出现了一定程度的下降，这在预期之内，对本模型的目标场景没有影响。 + +
+ + Accuracy & Recall + +
+ +## 引用 + +```bibtex +@misc{xiaomimimovlmiloco, + author = {Jiaze Li, Yuxun Qu, Jingyang Chen, Shijie Xu, Zhenru Lin, Junyou Zhu, Boshen Xu, Wenhui Tan, Pei Fu, JianZhong Ju, Zhenbo Luo, Jian Luan}, + title = {Xiaomi MiMo-VL-Miloco}, + year = {2025}, + howpublished = {\url{https://github.com/XiaoMi/xiaomi-mimo-vl-miloco}}, +} +``` + +## 联系方式 +欢迎通过邮箱联系我们：milm-plus@xiaomi.com。如果您有任何问题，可以随时在issue中提问。 \ No newline at end of file diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..482ced4 --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,24 @@ +{ + "": 151658, + "": 151657, + "<|box_end|>": 151649, + "<|box_start|>": 151648, + "<|endoftext|>": 151643, + "<|file_sep|>": 151664, + "<|fim_middle|>": 151660, + "<|fim_pad|>": 151662, + "<|fim_prefix|>": 151659, + "<|fim_suffix|>": 151661, + "<|im_end|>": 151645, + "<|im_start|>": 151644, + "<|image_pad|>": 151655, + "<|object_ref_end|>": 151647, + "<|object_ref_start|>": 151646, + "<|quad_end|>": 151651, + "<|quad_start|>": 151650, + "<|repo_name|>": 151663, + "<|video_pad|>": 151656, + "<|vision_end|>": 151653, + "<|vision_pad|>": 151654, + "<|vision_start|>": 151652 +} diff --git a/chat_template.json b/chat_template.json new file mode 100644 index 0000000..56aa25a --- /dev/null +++ b/chat_template.json @@ -0,0 +1,3 @@ +{ + "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are MiMo, an AI assistant developed by Xiaomi.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}" +} diff --git a/config.json b/config.json new file mode 100644 index 0000000..378298e --- /dev/null +++ b/config.json @@ -0,0 +1,68 @@ +{ + "architectures": [ + "Qwen2_5_VLForConditionalGeneration" + ], + "attention_bias": true, + "attention_dropout": 0.0, + "eos_token_id": 151645, + "hidden_act": "silu", + "hidden_size": 4096, + "image_token_id": 151655, + "initializer_range": 0.02, + "intermediate_size": 11008, + "max_position_embeddings": 128000, + "max_window_layers": 32, + "model_type": "qwen2_5_vl", + "num_attention_heads": 32, + "num_hidden_layers": 36, + "num_key_value_heads": 8, + "pad_token_id": 151643, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 1.0, + "mrope_section": [ + 16, + 24, + 24 + ], + "original_max_position_embeddings": 128000, + "rope_type": "default", + "type": "default" + }, + "rope_theta": 640000.0, + "sliding_window": 8192, + "tie_word_embeddings": false, + "torch_dtype": "float32", + "transformers_version": "4.51.3", + "use_cache": false, + "use_sliding_window": false, + "video_token_id": 151656, + "vision_config": { + "depth": 32, + "fullatt_block_indexes": [ + 7, + 15, + 23, + 31 + ], + "hidden_act": "silu", + "hidden_size": 1280, + "in_channels": 3, + "in_chans": 3, + "intermediate_size": 3456, + "model_type": "qwen2_5_vl", + "num_heads": 16, + "out_hidden_size": 4096, + "patch_size": 14, + "spatial_merge_size": 2, + "spatial_patch_size": 14, + "temporal_patch_size": 2, + "tokens_per_second": 2, + "torch_dtype": "float32", + "window_size": 112 + }, + "vision_end_token_id": 151653, + "vision_start_token_id": 151652, + "vision_token_id": 151654, + "vocab_size": 151680 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..889dcf8 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "eos_token_id": 151645, + "pad_token_id": 151643, + "transformers_version": "4.51.3", + "use_cache": false +} diff --git a/merges.txt b/merges.txt new file mode 100644 index 0000000..80c1a19 --- /dev/null +++ b/merges.txt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8831e4f1a044471340f7c0a83d7bd71306a5b867e95fd870f74d0c5308a904d5 +size 1671853 diff --git a/model-00001-of-00004.safetensors b/model-00001-of-00004.safetensors new file mode 100644 index 0000000..26a9880 --- /dev/null +++ b/model-00001-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7addf5ac1b8e571ba8a7ac95411b1cb218c8fe5d97b4a094bf5d7509d231eea4 +size 4924932064 diff --git a/model-00002-of-00004.safetensors b/model-00002-of-00004.safetensors new file mode 100644 index 0000000..fa9dac7 --- /dev/null +++ b/model-00002-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bbba5b17f49c549c6b18a1019c3d26a037dbe57c59d670eb7ac945dca30b6425 +size 4994899272 diff --git a/model-00003-of-00004.safetensors b/model-00003-of-00004.safetensors new file mode 100644 index 0000000..0d974a9 --- /dev/null +++ b/model-00003-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac2fe415fe8e7b3cb5b45443d4901d7b0e44b9cd3466d9d22565c5415a996e83 +size 4077753448 diff --git a/model-00004-of-00004.safetensors b/model-00004-of-00004.safetensors new file mode 100644 index 0000000..53e9236 --- /dev/null +++ b/model-00004-of-00004.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f2609279b917e58a78d009c06da2f817ec65c51b6018357e0c7f512e713bd41 +size 2614942032 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..bfab165 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,832 @@ +{ + "metadata": { + "total_size": 16612434432 + }, + "weight_map": { + "lm_head.weight": "model-00004-of-00004.safetensors", + "model.embed_tokens.weight": "model-00002-of-00004.safetensors", + "model.layers.0.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.1.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.14.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.16.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.17.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.17.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.20.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.21.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.23.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.24.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.25.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.27.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.27.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.28.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.28.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.29.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.29.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.29.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.3.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.30.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.30.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.30.self_attn.q_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.31.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.31.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.32.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.32.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.32.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.33.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.33.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.33.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.34.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.34.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.35.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.35.self_attn.k_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.35.self_attn.q_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.4.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.5.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.6.input_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model-00002-of-00004.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.7.input_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model-00003-of-00004.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00004.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model-00004-of-00004.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00004.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00004.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00004.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors", + "model.norm.weight": "model-00004-of-00004.safetensors", + "visual.blocks.0.attn.proj.bias": "model-00002-of-00004.safetensors", + "visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors", + "visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors", + "visual.blocks.0.mlp.down_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.0.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "visual.blocks.0.mlp.gate_proj.bias": "model-00003-of-00004.safetensors", + "visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.0.mlp.up_proj.bias": "model-00002-of-00004.safetensors", + "visual.blocks.0.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.0.norm1.weight": "model-00003-of-00004.safetensors", + "visual.blocks.0.norm2.weight": "model-00004-of-00004.safetensors", + "visual.blocks.1.attn.proj.bias": "model-00002-of-00004.safetensors", + "visual.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors", + "visual.blocks.1.attn.qkv.weight": "model-00002-of-00004.safetensors", + "visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.1.mlp.gate_proj.bias": "model-00002-of-00004.safetensors", + "visual.blocks.1.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "visual.blocks.1.mlp.up_proj.bias": "model-00002-of-00004.safetensors", + "visual.blocks.1.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.1.norm1.weight": "model-00001-of-00004.safetensors", + "visual.blocks.1.norm2.weight": "model-00004-of-00004.safetensors", + "visual.blocks.10.attn.proj.bias": "model-00002-of-00004.safetensors", + "visual.blocks.10.attn.proj.weight": "model-00002-of-00004.safetensors", + "visual.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors", + "visual.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors", + "visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.10.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "visual.blocks.10.mlp.up_proj.bias": "model-00003-of-00004.safetensors", + "visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors", + "visual.blocks.10.norm2.weight": "model-00002-of-00004.safetensors", + "visual.blocks.11.attn.proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.11.attn.proj.weight": "model-00003-of-00004.safetensors", + "visual.blocks.11.attn.qkv.bias": "model-00002-of-00004.safetensors", + "visual.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors", + "visual.blocks.11.mlp.down_proj.bias": "model-00003-of-00004.safetensors", + "visual.blocks.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.11.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "visual.blocks.11.mlp.up_proj.bias": "model-00002-of-00004.safetensors", + "visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.11.norm1.weight": "model-00004-of-00004.safetensors", + "visual.blocks.11.norm2.weight": "model-00003-of-00004.safetensors", + "visual.blocks.12.attn.proj.bias": "model-00003-of-00004.safetensors", + "visual.blocks.12.attn.proj.weight": "model-00003-of-00004.safetensors", + "visual.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors", + "visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors", + "visual.blocks.12.mlp.down_proj.bias": "model-00002-of-00004.safetensors", + "visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.12.norm1.weight": "model-00004-of-00004.safetensors", + "visual.blocks.12.norm2.weight": "model-00004-of-00004.safetensors", + "visual.blocks.13.attn.proj.bias": "model-00002-of-00004.safetensors", + "visual.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.13.attn.qkv.bias": "model-00002-of-00004.safetensors", + "visual.blocks.13.attn.qkv.weight": "model-00004-of-00004.safetensors", + "visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.13.mlp.gate_proj.bias": "model-00003-of-00004.safetensors", + "visual.blocks.13.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "visual.blocks.13.mlp.up_proj.bias": "model-00002-of-00004.safetensors", + "visual.blocks.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors", + "visual.blocks.13.norm2.weight": "model-00002-of-00004.safetensors", + "visual.blocks.14.attn.proj.bias": "model-00002-of-00004.safetensors", + "visual.blocks.14.attn.proj.weight": "model-00003-of-00004.safetensors", + "visual.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors", + "visual.blocks.14.attn.qkv.weight": "model-00002-of-00004.safetensors", + "visual.blocks.14.mlp.down_proj.bias": "model-00003-of-00004.safetensors", + "visual.blocks.14.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.14.mlp.up_proj.bias": "model-00003-of-00004.safetensors", + "visual.blocks.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "visual.blocks.14.norm1.weight": "model-00002-of-00004.safetensors", + "visual.blocks.14.norm2.weight": "model-00004-of-00004.safetensors", + "visual.blocks.15.attn.proj.bias": "model-00002-of-00004.safetensors", + "visual.blocks.15.attn.proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors", + "visual.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors", + "visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.15.mlp.gate_proj.bias": "model-00002-of-00004.safetensors", + "visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors", + "visual.blocks.15.norm2.weight": "model-00001-of-00004.safetensors", + "visual.blocks.16.attn.proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.16.attn.proj.weight": "model-00002-of-00004.safetensors", + "visual.blocks.16.attn.qkv.bias": "model-00003-of-00004.safetensors", + "visual.blocks.16.attn.qkv.weight": "model-00004-of-00004.safetensors", + "visual.blocks.16.mlp.down_proj.bias": "model-00003-of-00004.safetensors", + "visual.blocks.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "visual.blocks.16.mlp.gate_proj.bias": "model-00003-of-00004.safetensors", + "visual.blocks.16.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "visual.blocks.16.mlp.up_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.16.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "visual.blocks.16.norm1.weight": "model-00002-of-00004.safetensors", + "visual.blocks.16.norm2.weight": "model-00003-of-00004.safetensors", + "visual.blocks.17.attn.proj.bias": "model-00003-of-00004.safetensors", + "visual.blocks.17.attn.proj.weight": "model-00002-of-00004.safetensors", + "visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors", + "visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors", + "visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.17.mlp.gate_proj.bias": "model-00002-of-00004.safetensors", + "visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.17.mlp.up_proj.bias": "model-00003-of-00004.safetensors", + "visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.17.norm1.weight": "model-00002-of-00004.safetensors", + "visual.blocks.17.norm2.weight": "model-00001-of-00004.safetensors", + "visual.blocks.18.attn.proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.18.attn.proj.weight": "model-00002-of-00004.safetensors", + "visual.blocks.18.attn.qkv.bias": "model-00002-of-00004.safetensors", + "visual.blocks.18.attn.qkv.weight": "model-00002-of-00004.safetensors", + "visual.blocks.18.mlp.down_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "visual.blocks.18.mlp.gate_proj.bias": "model-00003-of-00004.safetensors", + "visual.blocks.18.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "visual.blocks.18.mlp.up_proj.bias": "model-00003-of-00004.safetensors", + "visual.blocks.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "visual.blocks.18.norm1.weight": "model-00002-of-00004.safetensors", + "visual.blocks.18.norm2.weight": "model-00001-of-00004.safetensors", + "visual.blocks.19.attn.proj.bias": "model-00002-of-00004.safetensors", + "visual.blocks.19.attn.proj.weight": "model-00003-of-00004.safetensors", + "visual.blocks.19.attn.qkv.bias": "model-00004-of-00004.safetensors", + "visual.blocks.19.attn.qkv.weight": "model-00004-of-00004.safetensors", + "visual.blocks.19.mlp.down_proj.bias": "model-00003-of-00004.safetensors", + "visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.19.mlp.gate_proj.bias": "model-00002-of-00004.safetensors", + "visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.19.mlp.up_proj.bias": "model-00003-of-00004.safetensors", + "visual.blocks.19.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.19.norm1.weight": "model-00002-of-00004.safetensors", + "visual.blocks.19.norm2.weight": "model-00004-of-00004.safetensors", + "visual.blocks.2.attn.proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.2.attn.proj.weight": "model-00002-of-00004.safetensors", + "visual.blocks.2.attn.qkv.bias": "model-00003-of-00004.safetensors", + "visual.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors", + "visual.blocks.2.mlp.down_proj.bias": "model-00002-of-00004.safetensors", + "visual.blocks.2.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.2.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.2.mlp.up_proj.bias": "model-00003-of-00004.safetensors", + "visual.blocks.2.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "visual.blocks.2.norm1.weight": "model-00002-of-00004.safetensors", + "visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors", + "visual.blocks.20.attn.proj.bias": "model-00003-of-00004.safetensors", + "visual.blocks.20.attn.proj.weight": "model-00002-of-00004.safetensors", + "visual.blocks.20.attn.qkv.bias": "model-00002-of-00004.safetensors", + "visual.blocks.20.attn.qkv.weight": "model-00003-of-00004.safetensors", + "visual.blocks.20.mlp.down_proj.bias": "model-00003-of-00004.safetensors", + "visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.20.mlp.gate_proj.bias": "model-00002-of-00004.safetensors", + "visual.blocks.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "visual.blocks.20.mlp.up_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "visual.blocks.20.norm1.weight": "model-00004-of-00004.safetensors", + "visual.blocks.20.norm2.weight": "model-00002-of-00004.safetensors", + "visual.blocks.21.attn.proj.bias": "model-00002-of-00004.safetensors", + "visual.blocks.21.attn.proj.weight": "model-00002-of-00004.safetensors", + "visual.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors", + "visual.blocks.21.attn.qkv.weight": "model-00003-of-00004.safetensors", + "visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.21.mlp.gate_proj.bias": "model-00002-of-00004.safetensors", + "visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.21.mlp.up_proj.bias": "model-00003-of-00004.safetensors", + "visual.blocks.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "visual.blocks.21.norm1.weight": "model-00002-of-00004.safetensors", + "visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors", + "visual.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.22.attn.qkv.bias": "model-00002-of-00004.safetensors", + "visual.blocks.22.attn.qkv.weight": "model-00003-of-00004.safetensors", + "visual.blocks.22.mlp.down_proj.bias": "model-00002-of-00004.safetensors", + "visual.blocks.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "visual.blocks.22.mlp.gate_proj.bias": "model-00002-of-00004.safetensors", + "visual.blocks.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "visual.blocks.22.norm1.weight": "model-00001-of-00004.safetensors", + "visual.blocks.22.norm2.weight": "model-00003-of-00004.safetensors", + "visual.blocks.23.attn.proj.bias": "model-00002-of-00004.safetensors", + "visual.blocks.23.attn.proj.weight": "model-00002-of-00004.safetensors", + "visual.blocks.23.attn.qkv.bias": "model-00003-of-00004.safetensors", + "visual.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors", + "visual.blocks.23.mlp.down_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.23.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.23.norm1.weight": "model-00003-of-00004.safetensors", + "visual.blocks.23.norm2.weight": "model-00003-of-00004.safetensors", + "visual.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.24.attn.proj.weight": "model-00003-of-00004.safetensors", + "visual.blocks.24.attn.qkv.bias": "model-00003-of-00004.safetensors", + "visual.blocks.24.attn.qkv.weight": "model-00003-of-00004.safetensors", + "visual.blocks.24.mlp.down_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.24.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.24.mlp.up_proj.bias": "model-00003-of-00004.safetensors", + "visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.24.norm1.weight": "model-00003-of-00004.safetensors", + "visual.blocks.24.norm2.weight": "model-00004-of-00004.safetensors", + "visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.25.attn.qkv.bias": "model-00003-of-00004.safetensors", + "visual.blocks.25.attn.qkv.weight": "model-00002-of-00004.safetensors", + "visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.25.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "visual.blocks.25.mlp.gate_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "visual.blocks.25.mlp.up_proj.bias": "model-00003-of-00004.safetensors", + "visual.blocks.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "visual.blocks.25.norm1.weight": "model-00003-of-00004.safetensors", + "visual.blocks.25.norm2.weight": "model-00003-of-00004.safetensors", + "visual.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.26.attn.proj.weight": "model-00003-of-00004.safetensors", + "visual.blocks.26.attn.qkv.bias": "model-00002-of-00004.safetensors", + "visual.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors", + "visual.blocks.26.mlp.down_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.26.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "visual.blocks.26.mlp.up_proj.bias": "model-00002-of-00004.safetensors", + "visual.blocks.26.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.26.norm1.weight": "model-00004-of-00004.safetensors", + "visual.blocks.26.norm2.weight": "model-00002-of-00004.safetensors", + "visual.blocks.27.attn.proj.bias": "model-00002-of-00004.safetensors", + "visual.blocks.27.attn.proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.27.attn.qkv.bias": "model-00001-of-00004.safetensors", + "visual.blocks.27.attn.qkv.weight": "model-00002-of-00004.safetensors", + "visual.blocks.27.mlp.down_proj.bias": "model-00002-of-00004.safetensors", + "visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.27.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.27.mlp.up_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.27.norm1.weight": "model-00003-of-00004.safetensors", + "visual.blocks.27.norm2.weight": "model-00001-of-00004.safetensors", + "visual.blocks.28.attn.proj.bias": "model-00002-of-00004.safetensors", + "visual.blocks.28.attn.proj.weight": "model-00003-of-00004.safetensors", + "visual.blocks.28.attn.qkv.bias": "model-00004-of-00004.safetensors", + "visual.blocks.28.attn.qkv.weight": "model-00003-of-00004.safetensors", + "visual.blocks.28.mlp.down_proj.bias": "model-00003-of-00004.safetensors", + "visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.28.mlp.gate_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.28.mlp.up_proj.bias": "model-00003-of-00004.safetensors", + "visual.blocks.28.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "visual.blocks.28.norm1.weight": "model-00003-of-00004.safetensors", + "visual.blocks.28.norm2.weight": "model-00001-of-00004.safetensors", + "visual.blocks.29.attn.proj.bias": "model-00002-of-00004.safetensors", + "visual.blocks.29.attn.proj.weight": "model-00003-of-00004.safetensors", + "visual.blocks.29.attn.qkv.bias": "model-00002-of-00004.safetensors", + "visual.blocks.29.attn.qkv.weight": "model-00002-of-00004.safetensors", + "visual.blocks.29.mlp.down_proj.bias": "model-00002-of-00004.safetensors", + "visual.blocks.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "visual.blocks.29.mlp.gate_proj.bias": "model-00002-of-00004.safetensors", + "visual.blocks.29.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "visual.blocks.29.mlp.up_proj.bias": "model-00002-of-00004.safetensors", + "visual.blocks.29.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "visual.blocks.29.norm1.weight": "model-00004-of-00004.safetensors", + "visual.blocks.29.norm2.weight": "model-00002-of-00004.safetensors", + "visual.blocks.3.attn.proj.bias": "model-00003-of-00004.safetensors", + "visual.blocks.3.attn.proj.weight": "model-00003-of-00004.safetensors", + "visual.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors", + "visual.blocks.3.attn.qkv.weight": "model-00002-of-00004.safetensors", + "visual.blocks.3.mlp.down_proj.bias": "model-00003-of-00004.safetensors", + "visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.3.mlp.gate_proj.bias": "model-00003-of-00004.safetensors", + "visual.blocks.3.mlp.gate_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.3.mlp.up_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.3.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "visual.blocks.3.norm1.weight": "model-00003-of-00004.safetensors", + "visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors", + "visual.blocks.30.attn.proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.30.attn.proj.weight": "model-00003-of-00004.safetensors", + "visual.blocks.30.attn.qkv.bias": "model-00002-of-00004.safetensors", + "visual.blocks.30.attn.qkv.weight": "model-00002-of-00004.safetensors", + "visual.blocks.30.mlp.down_proj.bias": "model-00003-of-00004.safetensors", + "visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.30.mlp.gate_proj.bias": "model-00002-of-00004.safetensors", + "visual.blocks.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "visual.blocks.30.mlp.up_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.30.norm1.weight": "model-00003-of-00004.safetensors", + "visual.blocks.30.norm2.weight": "model-00002-of-00004.safetensors", + "visual.blocks.31.attn.proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.31.attn.proj.weight": "model-00002-of-00004.safetensors", + "visual.blocks.31.attn.qkv.bias": "model-00002-of-00004.safetensors", + "visual.blocks.31.attn.qkv.weight": "model-00004-of-00004.safetensors", + "visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.31.mlp.gate_proj.bias": "model-00003-of-00004.safetensors", + "visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.31.mlp.up_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.31.norm1.weight": "model-00001-of-00004.safetensors", + "visual.blocks.31.norm2.weight": "model-00003-of-00004.safetensors", + "visual.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.4.attn.qkv.bias": "model-00003-of-00004.safetensors", + "visual.blocks.4.attn.qkv.weight": "model-00002-of-00004.safetensors", + "visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.4.mlp.up_proj.bias": "model-00003-of-00004.safetensors", + "visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.4.norm1.weight": "model-00002-of-00004.safetensors", + "visual.blocks.4.norm2.weight": "model-00001-of-00004.safetensors", + "visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.5.attn.qkv.bias": "model-00003-of-00004.safetensors", + "visual.blocks.5.attn.qkv.weight": "model-00003-of-00004.safetensors", + "visual.blocks.5.mlp.down_proj.bias": "model-00002-of-00004.safetensors", + "visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.5.mlp.gate_proj.bias": "model-00002-of-00004.safetensors", + "visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.5.mlp.up_proj.bias": "model-00003-of-00004.safetensors", + "visual.blocks.5.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors", + "visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors", + "visual.blocks.6.attn.proj.bias": "model-00003-of-00004.safetensors", + "visual.blocks.6.attn.proj.weight": "model-00002-of-00004.safetensors", + "visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors", + "visual.blocks.6.attn.qkv.weight": "model-00003-of-00004.safetensors", + "visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors", + "visual.blocks.6.mlp.gate_proj.bias": "model-00003-of-00004.safetensors", + "visual.blocks.6.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "visual.blocks.6.mlp.up_proj.bias": "model-00003-of-00004.safetensors", + "visual.blocks.6.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "visual.blocks.6.norm1.weight": "model-00003-of-00004.safetensors", + "visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors", + "visual.blocks.7.attn.proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.7.attn.proj.weight": "model-00004-of-00004.safetensors", + "visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors", + "visual.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors", + "visual.blocks.7.mlp.down_proj.bias": "model-00002-of-00004.safetensors", + "visual.blocks.7.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "visual.blocks.7.mlp.gate_proj.bias": "model-00002-of-00004.safetensors", + "visual.blocks.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.7.mlp.up_proj.weight": "model-00003-of-00004.safetensors", + "visual.blocks.7.norm1.weight": "model-00003-of-00004.safetensors", + "visual.blocks.7.norm2.weight": "model-00003-of-00004.safetensors", + "visual.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.8.attn.proj.weight": "model-00003-of-00004.safetensors", + "visual.blocks.8.attn.qkv.bias": "model-00002-of-00004.safetensors", + "visual.blocks.8.attn.qkv.weight": "model-00003-of-00004.safetensors", + "visual.blocks.8.mlp.down_proj.bias": "model-00003-of-00004.safetensors", + "visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.8.mlp.gate_proj.bias": "model-00004-of-00004.safetensors", + "visual.blocks.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors", + "visual.blocks.8.mlp.up_proj.bias": "model-00003-of-00004.safetensors", + "visual.blocks.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "visual.blocks.8.norm1.weight": "model-00003-of-00004.safetensors", + "visual.blocks.8.norm2.weight": "model-00001-of-00004.safetensors", + "visual.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors", + "visual.blocks.9.attn.qkv.bias": "model-00003-of-00004.safetensors", + "visual.blocks.9.attn.qkv.weight": "model-00002-of-00004.safetensors", + "visual.blocks.9.mlp.down_proj.bias": "model-00003-of-00004.safetensors", + "visual.blocks.9.mlp.down_proj.weight": "model-00003-of-00004.safetensors", + "visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.9.mlp.gate_proj.weight": "model-00003-of-00004.safetensors", + "visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00004.safetensors", + "visual.blocks.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors", + "visual.blocks.9.norm1.weight": "model-00004-of-00004.safetensors", + "visual.blocks.9.norm2.weight": "model-00003-of-00004.safetensors", + "visual.merger.ln_q.weight": "model-00003-of-00004.safetensors", + "visual.merger.mlp.0.bias": "model-00001-of-00004.safetensors", + "visual.merger.mlp.0.weight": "model-00003-of-00004.safetensors", + "visual.merger.mlp.2.bias": "model-00002-of-00004.safetensors", + "visual.merger.mlp.2.weight": "model-00002-of-00004.safetensors", + "visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors" + } +} diff --git a/preprocessor_config.json b/preprocessor_config.json new file mode 100644 index 0000000..ee08cdd --- /dev/null +++ b/preprocessor_config.json @@ -0,0 +1,29 @@ +{ + "do_convert_rgb": true, + "do_normalize": true, + "do_rescale": true, + "do_resize": true, + "image_mean": [ + 0.48145466, + 0.4578275, + 0.40821073 + ], + "image_processor_type": "Qwen2VLImageProcessor", + "image_std": [ + 0.26862954, + 0.26130258, + 0.27577711 + ], + "max_pixels": 12845056, + "merge_size": 2, + "min_pixels": 3136, + "patch_size": 14, + "processor_class": "Qwen2_5_VLProcessor", + "resample": 3, + "rescale_factor": 0.00392156862745098, + "size": { + "longest_edge": 12845056, + "shortest_edge": 3136 + }, + "temporal_patch_size": 2 +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..ac23c0a --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,31 @@ +{ + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "eos_token": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..51ebb3b --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa +size 11421896 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..ffecd7e --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,209 @@ +{ + "add_bos_token": false, + "add_prefix_space": false, + "added_tokens_decoder": { + "151643": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151644": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151645": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151646": { + "content": "<|object_ref_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151647": { + "content": "<|object_ref_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151648": { + "content": "<|box_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151649": { + "content": "<|box_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151650": { + "content": "<|quad_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151651": { + "content": "<|quad_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151652": { + "content": "<|vision_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151653": { + "content": "<|vision_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151654": { + "content": "<|vision_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151655": { + "content": "<|image_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151656": { + "content": "<|video_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151657": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151658": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151659": { + "content": "<|fim_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151660": { + "content": "<|fim_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151661": { + "content": "<|fim_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151662": { + "content": "<|fim_pad|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151663": { + "content": "<|repo_name|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151664": { + "content": "<|file_sep|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "<|im_start|>", + "<|im_end|>", + "<|object_ref_start|>", + "<|object_ref_end|>", + "<|box_start|>", + "<|box_end|>", + "<|quad_start|>", + "<|quad_end|>", + "<|vision_start|>", + "<|vision_end|>", + "<|vision_pad|>", + "<|image_pad|>", + "<|video_pad|>" + ], + "bos_token": null, + "chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are MiMo, an AI assistant developed by Xiaomi.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within XML tags:\\n\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n\\n\\nFor each function call, return a json object with function name and arguments within XML tags:\\n\\n{\\\"name\\\": , \\\"arguments\\\": }\\n<|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are MiMo, an AI assistant developed by Xiaomi.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n\\n' }}\n {{- message.content }}\n {{- '\\n' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n", + "clean_up_tokenization_spaces": false, + "eos_token": "<|im_end|>", + "errors": "replace", + "extra_special_tokens": {}, + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "processor_class": "Qwen2_5_VLProcessor", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +} diff --git a/vocab.json b/vocab.json new file mode 100644 index 0000000..6c49fc6 --- /dev/null +++ b/vocab.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca10d7e9fb3ed18575dd1e277a2579c16d108e32f27439684afa0e10b1440910 +size 2776833